Uniqueness and patterns in penguin breast feathers have been used by a video surveillance system to monitor tens of thousands of the birds, according to the BBC:

Professor Barham said: “We set a camera up in a location where the penguins will regularly walk past on their way to or from the sea.

“Every image that the camera processes is then sent back to a computer.”

The software has been trained to recognise if there are any penguins in the camera’s field of vision. If there are, it looks at the spot patterns to determine whether it is a bird that it recognises or new penguin. It then records and ID number and the date, time and location of the sighting.

How do the scientists prove uniqueness? Naturally the system will be soon discussed in terms of leopards, zebras, cheetahs and other patterned animals. Even if humans do not have uniquely patterned feathers or fur, it seems to me this technology will eventually make its way into correlation engines that can track a suspect with certain features and provide a single storyline across multiple cameras. On the other end of the spectrum, pun not intended, humans are getting more savvy at using infrared LED to completely disguise themselves from night-vision surveillance. This defensive maneuver might prevent identification of the person, but a pattern-matching system perhaps would still be able to track and report on that person’s movements.

While the privacy debate continues around video surveillance, the BBC also reports that audio surveillance has started to be integrated into camera systems:

Dr David Brown, from the University of Portsmouth, said: “The visual-recognition software will be able to identify visual patterns but for the next stage we want to get the camera to pivot if it hears a certain type of sound.

“So, if in a car park someone smashes a window, the camera would turn to look at them and the camera operator would be alerted.

This seems a reduction of usefulness, in some ways, as sounds are often a distraction more than an aid. If you read the article you will find some optimism for pattern-matching technology. For example, the researchers plan to be able to detect breaking glass versus other sounds. They do not mention if someone throwing a bottle would actually be a simple defensive measure to divert the camera. And what if you throw the bottle at the same time that you break a window?

I would love to test these systems.